An intelligent regional geological disaster risk assessment method and system

Abstract

The application discloses a regional geological disaster risk intelligent evaluation method and system, and relates to the technical field of intelligent evaluation.The system runs, through integration of real-time sensors and satellite remote sensing data, collects various real-time data related to debris flow, pre-processes original data, and stores the original data into a data storage system.Based on the collected data, a physical model and a machine learning model are constructed, and after calculation, the following are obtained: a debris flow disaster risk index MRI, a rainfall intensity coefficient RIC, a geological vulnerability coefficient GVC, and a hydrodynamic pressure coefficient HPC.The probability of debris flow occurrence is predicted.According to the model output result, the debris flow disaster risk index MRI is compared with a preset first safety threshold M and a second safety threshold N, the risk level of debris flow occurrence is evaluated, different regions are classified and managed, a debris flow warning is issued according to real-time monitoring data and risk evaluation results, and automatic emergency response measures are supported.

Description

Technical Field

[0001] The present invention relates to the field of intelligent assessment technology, and in particular to a method and system for intelligent assessment of regional geological disaster risks. Background Art

[0002] Debris flows, a regional geological disaster, are a common and severe natural disaster in mountainous and hilly areas. They are typically triggered by external factors such as heavy rainfall, snowmelt, and earthquakes. They are characterized by suddenness, destructive power, and widespread impact. Debris flows often cause severe consequences such as traffic disruptions, housing damage, and casualties, posing a significant threat to the local socioeconomic and ecological environment. Traditional methods for monitoring and warning debris flows often rely on single data sources or empirical judgment, making them incapable of accurately predicting and rapidly responding to debris flow occurrences.

[0003] However, existing methods for monitoring debris flow disasters suffer from numerous shortcomings when dealing with complex environments and changing meteorological conditions. Traditional disaster monitoring systems often lack real-time integration of multi-source data, making them unable to effectively capture key triggers of debris flow occurrences, such as sudden heavy rainfall or drastic changes in geological conditions. Furthermore, existing warning mechanisms often rely on historical experience or human judgment, lacking in-depth analysis and modeling of complex data. This results in low warning accuracy and the risk of false alarms and missed alerts. These shortcomings are primarily due to the inadequate analysis of debris flow triggering factors and the limited data processing and modeling capabilities of existing monitoring technologies. When heavy rainfall or geological changes occur in a region, traditional systems often fail to issue timely warnings due to their slow data integration and lack of real-time analysis capabilities, resulting in delayed emergency response. This delay not only delays rescue efforts but can also exacerbate the devastation, leading to severe economic losses and casualties. Furthermore, existing systems lack the ability to adaptively adjust model parameters, making it difficult to effectively respond to dynamic environmental changes, thereby increasing the error range of predictions. The fundamental reason for the existing defects lies in the insufficient real-time monitoring and modeling capabilities of complex geological and meteorological conditions. Therefore, the intelligent assessment system for debris flow disasters needs to be further optimized to cope with rapidly changing environments and sudden disasters, and to improve the accuracy and timeliness of early warnings. Summary of the Invention

[0004] In response to the deficiencies of the existing technology, the present invention provides a method and system for intelligent assessment of regional geological disaster risks, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a regional geological disaster risk intelligent assessment system, including a data acquisition module, a data preprocessing module, a debris flow model construction and analysis module, a risk assessment module, an early warning emergency response module, and a model optimization module;

[0006] The data acquisition module is used to collect a variety of real-time data related to debris flow, including meteorological data, geological data and hydrological data, by integrating real-time sensors and satellite remote sensing data;

[0007] The data preprocessing module is used to clean, format and reduce noise of the original data, complete missing data, remove abnormal data, and store it in the data storage system;

[0008] The debris flow model construction and analysis module is used to build a physical model and a machine learning model based on the collected data, and obtain the following after calculation: the debris flow disaster risk index MRI, the rainfall intensity coefficient RIC, the geological vulnerability coefficient GVC and the hydrodynamic pressure coefficient HPC, and predict the probability of debris flow occurrence. The model will combine the key parameters of topography, rainfall and soil moisture for analysis;

[0009] The risk assessment module is used to evaluate the risk level of debris flow occurrence based on the model output results by comparing the debris flow disaster risk index MRI with the preset first safety threshold M and second safety threshold N, and classify and manage different areas;

[0010] The early warning and emergency response module is used to issue debris flow warnings based on real-time monitoring data and risk assessment results. Warning information is transmitted to relevant departments and the public through text messages, alarms, and application notifications, supporting automated emergency response measures, including road closures and evacuations.

[0011] The model optimization module is used to self-adjust and optimize the debris flow prediction model using historical data and real-time feedback.

[0012] Preferably, the data acquisition module includes a meteorological data acquisition unit, a geological data acquisition unit and a hydrological data acquisition unit;

[0013] The meteorological data acquisition unit is used to collect meteorological data related to debris flow in real time by integrating automatic rain gauge, weather station and radar rainfall monitoring system, including rainfall amount, rainfall intensity and rainfall duration, to obtain: total rainfall P t , rainfall intensity I r and the cumulative rainfall threshold P th ;

[0014] The geological data acquisition unit is used to collect data related to geological fragility in real time by integrating GPS equipment, laser rangefinder and soil moisture sensor, including terrain slope, soil moisture content and rock fragmentation, to obtain: slope S, soil moisture content W s , rock crushing degree R f and vegetation coverage V c ;

[0015] The hydrological data acquisition unit is used to collect hydrological data related to hydrodynamic pressure in real time through a flow meter, an ultrasonic water level meter and a pressure sensor, including surface water flow, water depth and river runoff information, to obtain: surface runoff flow Q, water depth D, slope effect S e , River Basin Area A f and the watershed area normalization factor A max .

[0016] Preferably, the data preprocessing module includes a data preprocessing unit;

[0017] The data preprocessing unit is used to clean the collected raw data, remove noise and invalid data, convert the cleaned data into a unified format, ensure that data from different sources can be compatible in subsequent analysis, complete missing data, process missing key data points through interpolation or machine learning algorithms, and store them in a data storage system.

[0018] Preferably, the debris flow model construction and analysis module includes a physical model construction unit, a machine learning model construction unit and a risk coefficient calculation unit;

[0019] The physical model building unit is used to build a physical model for debris flow analysis based on topography, rainfall and soil moisture parameters, including a soil erosion model and a slope stability model;

[0020] The machine learning model building unit is used to build a machine learning model for debris flow probability prediction based on historical data and real-time collected data, including a neural network and a random forest model;

[0021] The risk coefficient calculation unit is used to calculate the debris flow disaster risk index MRI and its three key coefficients: rainfall intensity coefficient RIC, geological vulnerability coefficient GVC and hydrodynamic pressure coefficient HPC through the model, so as to predict the probability of debris flow occurrence;

[0022] The debris flow disaster risk index MRI is calculated by the following formula:

[0023] ;

[0024] Where RIC represents the rainfall intensity coefficient, GVC represents the geological vulnerability coefficient, and HPC represents the hydrodynamic pressure coefficient. They represent the weight coefficients of rainfall intensity coefficient RIC, geological vulnerability coefficient GVC and hydrodynamic pressure coefficient HPC respectively;

[0025] The rainfall intensity coefficient RIC is calculated using the following formula:

[0026] ;

[0027] Where, P t represents the total rainfall, I r represents rainfall intensity, P th represents the cumulative rainfall threshold, T r Indicates the duration of rainfall, w t represents the time weight factor, T max Indicates the upper limit of reference rainfall time.

[0028] Preferably, the geological vulnerability coefficient GVC is calculated using the following formula:

[0029] ;

[0030] Where S represents the slope, W s represents soil moisture content, R f Indicates the rock fragmentation, V c represents the vegetation coverage rate, Bg represents the probability of debris flow caused by bedrock fragility, Represents slope S, soil moisture W s and vegetation coverage V c The weight value of .

[0031] Preferably, the hydrodynamic pressure coefficient HPC is calculated by the following formula:

[0032] ;

[0033] Where Q represents the surface runoff flow, D represents the water depth, and S e represents the slope effect, A f represents the river basin area, A max represents the watershed area normalization factor.

[0034] Preferably, the risk assessment module includes a threshold comparison unit and a regional risk classification unit;

[0035] The threshold comparison unit is used to compare the debris flow disaster risk index MRI with the preset first safety threshold M and second safety threshold N to evaluate the risk level of debris flow:

[0036] When the debris flow disaster risk index MRI is less than or equal to the first safety threshold M, it is assessed as the first risk level. Within this range, the probability of debris flow occurrence is less than 30%, and it does not pose a threat to people, infrastructure and ecological environment in the area. Under this condition, the system maintains routine monitoring and no emergency response measures are required.

[0037] When the debris flow risk index MRI is greater than the first safety threshold M and less than or equal to the second safety threshold N, it is assessed as the second risk level. At this time, the probability of debris flow occurrence is 40%-50%. It is recommended to strengthen monitoring and remind relevant departments to take preventive measures, including raising the warning level, initiating local emergency preparations, and closely monitoring weather and geological changes in high-risk areas.

[0038] When the debris flow disaster risk index MRI is greater than the second safety threshold N, it is assessed as the third risk level. At this time, the risk of debris flow is greater than 50%. The emergency response mechanism needs to be activated immediately, and relevant departments need to be notified and the public needs to be warned. Road closures, personnel evacuations, and emergency deployment of rescue resources are required to ensure personal safety and minimize property losses.

[0039] The regional risk classification unit is used to classify and manage monitoring areas based on different risk levels and determine the priority of each area to facilitate the planning and execution of subsequent emergency responses.

[0040] Preferably, the early warning emergency response module includes an early warning generation unit and an emergency measure execution unit;

[0041] The warning generation unit is used to automatically generate debris flow warning information based on real-time monitoring data and risk assessment results, including detailed content of potential risks and the scope of the affected area, and transmit the debris flow warning information to relevant government departments and the public through SMS, alarm bells and application notification channels;

[0042] The emergency measures execution unit is used to automatically trigger preset emergency response measures according to the early warning information, including closing roads in the affected area, evacuating people and initiating the deployment of rescue resources.

[0043] Preferably, the model optimization module includes a historical data feedback unit and a model adjustment unit;

[0044] The historical data feedback unit is used to collect historical data and feedback information after the debris flow disaster occurs, and optimize and adaptively adjust the parameters of the existing physical model and machine learning model based on the feedback data;

[0045] The model adjustment unit is used to continuously update and iterate the model based on new data during system operation to ensure the adaptability and robustness of the debris flow risk prediction model under different environments and conditions.

[0046] A regional geological disaster risk intelligent assessment method comprises the following steps:

[0047] Step 1: Collect a variety of real-time data related to debris flows, including meteorological data, geological data, and hydrological data, by integrating real-time sensors and satellite remote sensing data;

[0048] Step 2: Clean, format, and reduce noise of the original data, complete missing data, remove abnormal data, and store it in the data storage system;

[0049] Step 3: Based on the collected data, a physical model and a machine learning model are constructed to calculate the following: debris flow risk index MRI, rainfall intensity coefficient RIC, geological vulnerability coefficient GVC, and hydrodynamic pressure coefficient HPC. The probability of debris flow occurrence is predicted by the model, which combines key parameters such as topography, rainfall, and soil moisture for analysis.

[0050] Step 4: Based on the model output, the debris flow disaster risk index MRI is compared with the preset first safety threshold M and second safety threshold N to assess the risk level of debris flow and classify and manage different areas;

[0051] Step 5: Based on real-time monitoring data and risk assessment results, a debris flow warning is issued. Warning information is transmitted to relevant departments and the public via text messages, alarms, and app notifications, supporting automated emergency response measures, including road closures and evacuations.

[0052] Step 6: Use historical data and real-time feedback to self-adjust and optimize the debris flow prediction model.

[0053] The present invention provides a method and system for intelligently assessing regional geological disaster risks, which has the following beneficial effects:

[0054] (1) When the system is running, it collects a variety of real-time data related to debris flows by integrating real-time sensors and satellite remote sensing data, preprocesses the original data, and stores it in the data storage system. Based on the collected data, it builds a physical model and a machine learning model, and obtains the following after calculation: debris flow disaster risk index MRI, rainfall intensity coefficient RIC, geological vulnerability coefficient GVC and hydrodynamic pressure coefficient HPC, and predicts the probability of debris flow. According to the output of the model, the debris flow disaster risk index MRI is compared with the preset first safety threshold M and second safety threshold N to evaluate the risk level of debris flow, and classify and manage different areas. According to the real-time monitoring data and risk assessment results, a debris flow warning is issued to support automated emergency response measures, including road closure and personnel evacuation. The debris flow prediction model is self-adjusted and optimized using historical data and real-time feedback.

[0055] (2) This regional geological disaster risk intelligent assessment system achieves real-time monitoring and accurate assessment of debris flow risks through the collaborative work of six major modules. The data acquisition module uses a combination of sensors, satellite remote sensing and other technologies to obtain important meteorological, geological, hydrological and other data from multiple dimensions; the data preprocessing module effectively cleans and completes the original data to ensure high-quality data input; the debris flow model construction and analysis module combines physical models with machine learning algorithms to accurately calculate the debris flow disaster risk index and predict the probability of potential disasters. Through the collaborative work of these modules, the system can comprehensively and real-timely assess the risk of debris flow, providing a solid data foundation for subsequent early warning and response.

[0056] (3) Compared with traditional debris flow monitoring methods, this intelligent assessment system has achieved significant improvements in risk assessment and early warning response. First, the risk assessment module can automatically classify and manage areas of different risk levels by comparing the debris flow disaster risk index with the preset safety threshold, and propose targeted early warning and emergency response measures. Second, the early warning and emergency response module relies on real-time data and model output to quickly generate early warning information and transmit it to relevant departments and the public through multiple channels in real time, greatly improving the timeliness and accuracy of the early warning. Compared with traditional systems, it reduces human judgment and reliance on experience, significantly reducing the risk of false alarms and missed alarms.

[0057] (4) Through the model optimization module, the system also has self-learning and self-adaptive capabilities. It can automatically optimize the prediction model based on historical disaster data and real-time feedback, continuously improving the prediction accuracy and system adaptability. This optimization mechanism enables the system to effectively respond to dynamic changes in environmental and geological conditions and maintain the long-term effectiveness and reliability of the prediction. Overall, compared with existing technical means, this system not only significantly improves the accuracy of data integration, model construction and risk assessment, but also brings a qualitative leap in the speed and reliability of early warning and emergency response, providing strong technical support for reducing the losses caused by debris flow disasters and improving the efficiency of emergency rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a block diagram of a regional geological disaster risk intelligent assessment system of the present invention;

[0059] Figure 2 This is a schematic diagram of the steps of a regional geological disaster risk intelligent assessment method of the present invention. DETAILED DESCRIPTION

[0060] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0061] Example 1

[0062] The present invention provides a regional geological disaster risk intelligent assessment system, please refer to Figure 1 , including data acquisition module, data preprocessing module, debris flow model construction and analysis module, risk assessment module, early warning emergency response module, and model optimization module;

[0063] The data acquisition module is used to collect a variety of real-time data related to debris flow, including meteorological data, geological data and hydrological data, by integrating real-time sensors and satellite remote sensing data;

[0064] The data preprocessing module is used to clean, format and reduce noise of the original data, complete missing data, remove abnormal data, and store it in the data storage system;

[0065] The debris flow model construction and analysis module is used to build a physical model and a machine learning model based on the collected data, and obtain the following after calculation: the debris flow disaster risk index MRI, the rainfall intensity coefficient RIC, the geological vulnerability coefficient GVC and the hydrodynamic pressure coefficient HPC, and predict the probability of debris flow occurrence. The model will combine the key parameters of topography, rainfall and soil moisture for analysis;

[0066] The risk assessment module is used to evaluate the risk level of debris flow occurrence based on the model output results by comparing the debris flow disaster risk index MRI with the preset first safety threshold M and second safety threshold N, and classify and manage different areas;

[0067] The early warning and emergency response module is used to issue debris flow warnings based on real-time monitoring data and risk assessment results. Warning information is transmitted to relevant departments and the public through text messages, alarms, and application notifications, supporting automated emergency response measures, including road closures and evacuations.

[0068] The model optimization module is used to self-adjust and optimize the debris flow prediction model using historical data and real-time feedback.

[0069] In this embodiment, by integrating real-time sensors and satellite remote sensing data, various real-time data related to debris flows are collected, the raw data are preprocessed and stored in a data storage system, and a physical model and a machine learning model are constructed based on the collected data. After calculation, the following are obtained: the debris flow disaster risk index MRI, the rainfall intensity coefficient RIC, the geological vulnerability coefficient GVC and the hydrodynamic pressure coefficient HPC, and the probability of debris flow occurrence is predicted. According to the model output results, the debris flow disaster risk index MRI is compared with the preset first safety threshold M and second safety threshold N to evaluate the risk level of debris flow occurrence, and different areas are classified and managed. Based on the real-time monitoring data and risk assessment results, a debris flow warning is issued to support automated emergency response measures, including road closures and personnel evacuation. Historical data and real-time feedback are used to self-adjust and optimize the debris flow prediction model.

[0070] Example 2

[0071] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes a meteorological data acquisition unit, a geological data acquisition unit and a hydrological data acquisition unit;

[0072] The meteorological data acquisition unit is used to collect meteorological data related to debris flow in real time by integrating automatic rain gauge, weather station and radar rainfall monitoring system, including rainfall amount, rainfall intensity and rainfall duration, to obtain: total rainfall P t , rainfall intensity I r and the cumulative rainfall threshold P th ;

[0073] The geological data acquisition unit is used to collect data related to geological fragility in real time by integrating GPS equipment, laser rangefinder and soil moisture sensor, including terrain slope, soil moisture content and rock fragmentation, to obtain: slope S, soil moisture content W s , rock crushing degree R f and vegetation coverage V c ;

[0074] The hydrological data acquisition unit is used to collect hydrological data related to hydrodynamic pressure in real time through a flow meter, an ultrasonic water level meter and a pressure sensor, including surface water flow, water depth and river runoff information, to obtain: surface runoff flow Q, water depth D, slope effect S e , River Basin Area A f and the watershed area normalization factor A max .

[0075] The data preprocessing module includes a data preprocessing unit;

[0076] The data preprocessing unit is used to clean the collected raw data, remove noise and invalid data, convert the cleaned data into a unified format, ensure that data from different sources can be compatible in subsequent analysis, complete missing data, process missing key data points through interpolation or machine learning algorithms, and store them in a data storage system.

[0077] In this embodiment, by integrating automated meteorological, geological, and hydrological data acquisition units, the system can acquire and process multi-dimensional data related to debris flows in real time, including key factors such as rainfall, topography, soil, and hydrology. The data preprocessing module further ensures high-quality data input by removing noise, formatting, and completing data, ensuring that data from different sources can be processed compatibly. The overall system can improve the accuracy and efficiency of data processing, providing a reliable foundation for subsequent debris flow risk assessment and prediction, thereby improving the accuracy and response speed of disaster warnings and reducing the false alarm and missed alarm rates in risk management.

[0078] Example 3

[0079] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the debris flow model construction and analysis module includes a physical model construction unit, a machine learning model construction unit and a risk coefficient calculation unit;

[0080] The physical model building unit is used to build a physical model for debris flow analysis based on topography, rainfall and soil moisture parameters, including a soil erosion model and a slope stability model;

[0081] The machine learning model building unit is used to build a machine learning model for debris flow probability prediction based on historical data and real-time collected data, including a neural network and a random forest model;

[0082] The risk coefficient calculation unit is used to calculate the debris flow disaster risk index MRI and its three key coefficients: rainfall intensity coefficient RIC, geological vulnerability coefficient GVC and hydrodynamic pressure coefficient HPC through the model, so as to predict the probability of debris flow occurrence;

[0083] The debris flow disaster risk index MRI is calculated by the following formula:

[0084] ;

[0085] Where RIC represents the rainfall intensity coefficient, GVC represents the geological vulnerability coefficient, and HPC represents the hydrodynamic pressure coefficient. They represent the weight coefficients of rainfall intensity coefficient RIC, geological vulnerability coefficient GVC and hydrodynamic pressure coefficient HPC respectively;

[0086] The rainfall intensity coefficient RIC is calculated using the following formula:

[0087] ;

[0088] Where, P t represents the total rainfall, I r represents rainfall intensity, P th represents the cumulative rainfall threshold, T r Indicates the duration of rainfall, w t represents the time weight factor, T max Indicates the upper limit of reference rainfall time.

[0089] The geological vulnerability coefficient GVC is calculated using the following formula:

[0090] ;

[0091] Where S represents the slope, W s represents soil moisture content, R f Indicates the rock fragmentation, V c represents the vegetation coverage rate, Bg represents the probability of debris flow caused by bedrock fragility, Represents slope S, soil moisture W s and vegetation coverage V c The weight value of .

[0092] The hydrodynamic pressure coefficient HPC is calculated by the following formula:

[0093] ;

[0094] Where Q represents the surface runoff flow, D represents the water depth, and S e represents the slope effect, A f represents the river basin area, A max represents the watershed area normalization factor.

[0095] In this embodiment, by combining the construction of physical models with machine learning models, the system can comprehensively consider various factors that affect the occurrence of debris flows, including topography, rainfall, soil moisture content, etc., and construct soil erosion models and slope stability models to improve the accuracy of the analysis. At the same time, the machine learning model continuously optimizes the probability prediction of debris flow based on historical data and real-time data, thereby improving the accuracy and flexibility of the prediction. By calculating the rainfall intensity coefficient, geological vulnerability coefficient, and hydrodynamic pressure coefficient, the system can quantify the debris flow disaster risk index and achieve an accurate assessment of the probability of debris flow occurrence. The overall effect significantly improves the scientific nature and accuracy of debris flow risk prediction, and provides a reliable basis for relevant disaster prevention and mitigation decisions.

[0096] Example 4

[0097] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the risk assessment module includes a threshold comparison unit and a regional risk classification unit;

[0098] The threshold comparison unit is used to compare the debris flow disaster risk index MRI with the preset first safety threshold M and second safety threshold N to evaluate the risk level of debris flow:

[0099] When the debris flow disaster risk index MRI is less than or equal to the first safety threshold M, it is assessed as the first risk level. Within this range, the probability of debris flow occurrence is less than 30%, and it does not pose a threat to people, infrastructure and ecological environment in the area. Under this condition, the system maintains routine monitoring and no emergency response measures are required.

[0100] When the debris flow risk index MRI is greater than the first safety threshold M and less than or equal to the second safety threshold N, it is assessed as the second risk level. At this time, the probability of debris flow occurrence is 40%-50%. It is recommended to strengthen monitoring and remind relevant departments to take preventive measures, including raising the warning level, initiating local emergency preparations, and closely monitoring weather and geological changes in high-risk areas.

[0101] When the debris flow disaster risk index MRI is greater than the second safety threshold N, it is assessed as the third risk level. At this time, the risk of debris flow is greater than 50%. The emergency response mechanism needs to be activated immediately, and relevant departments need to be notified and the public needs to be warned. Road closures, personnel evacuations, and emergency deployment of rescue resources are required to ensure personal safety and minimize property losses.

[0102] The regional risk classification unit is used to classify and manage monitoring areas based on different risk levels and determine the priority of each area to facilitate the planning and execution of subsequent emergency responses.

[0103] The early warning emergency response module includes an early warning generation unit and an emergency measure execution unit;

[0104] The warning generation unit is used to automatically generate debris flow warning information based on real-time monitoring data and risk assessment results, including detailed content of potential risks and the scope of the affected area, and transmit the debris flow warning information to relevant government departments and the public through SMS, alarm bells and application notification channels;

[0105] The emergency measures execution unit is used to automatically trigger preset emergency response measures according to the early warning information, including closing roads in the affected area, evacuating people and initiating the deployment of rescue resources.

[0106] The model optimization module includes a historical data feedback unit and a model adjustment unit;

[0107] The historical data feedback unit is used to collect historical data and feedback information after the debris flow disaster occurs, and optimize and adaptively adjust the parameters of the existing physical model and machine learning model based on the feedback data;

[0108] The model adjustment unit is used to continuously update and iterate the model based on new data during system operation to ensure the adaptability and robustness of the debris flow risk prediction model under different environments and conditions.

[0109] In this embodiment, the beneficial effect of the present invention is that, through the risk assessment mechanism of threshold comparison and regional risk classification, the system can accurately classify different levels of debris flow disaster risk index MRI, ensuring that areas with different risk levels receive corresponding management and monitoring. The early warning emergency response module can achieve timely notification to relevant departments and the public by automatically generating and publishing debris flow early warning information, and trigger automated emergency measures, including road closures and personnel evacuation, which greatly improves the speed and efficiency of emergency response. The model optimization module enables the system to adapt to changing environments through real-time data feedback and continuous model adjustment, ensuring long-term prediction accuracy and robustness, thereby further improving the prevention and control capabilities of debris flow disasters and the efficiency of post-disaster recovery.

[0110] Example 5

[0111] A regional geological disaster risk intelligent assessment method, please refer to Figure 2 , specifically: including the following steps:

[0112] Step 1: Collect a variety of real-time data related to debris flows, including meteorological data, geological data, and hydrological data, by integrating real-time sensors and satellite remote sensing data;

[0113] Step 2: Clean, format, and reduce noise of the original data, complete missing data, remove abnormal data, and store it in the data storage system;

[0114] Step 3: Based on the collected data, a physical model and a machine learning model are constructed to calculate the following: debris flow risk index MRI, rainfall intensity coefficient RIC, geological vulnerability coefficient GVC, and hydrodynamic pressure coefficient HPC. The probability of debris flow occurrence is predicted by the model, which combines key parameters such as topography, rainfall, and soil moisture for analysis.

[0115] Step 4: Based on the model output, the debris flow disaster risk index MRI is compared with the preset first safety threshold M and second safety threshold N to assess the risk level of debris flow and classify and manage different areas;

[0116] Step 5: Based on real-time monitoring data and risk assessment results, a debris flow warning is issued. Warning information is transmitted to relevant departments and the public via text messages, alarms, and app notifications, supporting automated emergency response measures, including road closures and evacuations.

[0117] Step 6: Use historical data and real-time feedback to self-adjust and optimize the debris flow prediction model.

[0118] In this embodiment, efficient monitoring, assessment and early warning of debris flow risks are achieved through a systematic process. By integrating real-time sensors and satellite remote sensing data, the system can comprehensively and accurately collect multi-dimensional data; the data preprocessing step ensures the accuracy and completeness of the data, thereby improving the reliability of the model analysis. Based on the physical model and machine learning model, the system can accurately calculate the debris flow disaster risk index MRI and classify and manage the risk levels of different areas. The real-time early warning mechanism notifies relevant departments and the public through multiple channels, quickly responds to potential disasters, and greatly improves the timeliness and accuracy of the early warning. The model self-optimization function ensures that the system maintains efficient predictive capabilities in the face of a changing environment, thereby effectively reducing the risks and losses caused by debris flow disasters.

[0119] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A regional geological disaster risk intelligent assessment system, characterized by: It includes data acquisition module, data preprocessing module, debris flow model construction and analysis module, risk assessment module, early warning and emergency response module, and model optimization module; The data acquisition module is used to collect a variety of real-time data related to debris flow, including meteorological data, geological data and hydrological data, by integrating real-time sensors and satellite remote sensing data; The data preprocessing module is used to clean, format and reduce noise of the original data, complete missing data, remove abnormal data, and store it in the data storage system; The debris flow model construction and analysis module is used to build a physical model and a machine learning model based on the collected data, and obtain the following after calculation: the debris flow disaster risk index MRI, the rainfall intensity coefficient RIC, the geological vulnerability coefficient GVC and the hydrodynamic pressure coefficient HPC, and predict the probability of debris flow occurrence. The model will combine the key parameters of topography, rainfall and soil moisture for analysis; The debris flow model construction and analysis module includes a physical model construction unit, a machine learning model construction unit and a risk coefficient calculation unit; The physical model building unit is used to build a physical model for debris flow analysis based on topography, rainfall and soil moisture parameters, including a soil erosion model and a slope stability model; The machine learning model building unit is used to build a machine learning model for debris flow probability prediction based on historical data and real-time collected data, including a neural network and a random forest model; The risk coefficient calculation unit is used to calculate the debris flow disaster risk index MRI and its three key coefficients: rainfall intensity coefficient RIC, geological vulnerability coefficient GVC and hydrodynamic pressure coefficient HPC through the model, so as to predict the probability of debris flow occurrence; The debris flow disaster risk index MRI is calculated by the following formula: MRI = α*RIC + β*GVC + γ*HPC; Where RIC represents the rainfall intensity coefficient, GVC represents the geological vulnerability coefficient, HPC represents the hydrodynamic pressure coefficient, α, β, and γ represent the weight coefficients of the rainfall intensity coefficient RIC, the geological vulnerability coefficient GVC, and the hydrodynamic pressure coefficient HPC, respectively; The rainfall intensity coefficient RIC is calculated using the following formula: Where, P t represents the total rainfall, I r represents rainfall intensity, P th represents the cumulative rainfall threshold, T r Indicates the duration of rainfall, w t represents the time weight factor, T max Indicates the upper limit of reference rainfall time; The geological vulnerability coefficient GVC is calculated using the following formula: Where S represents the slope, W s represents soil moisture content, R f Indicates the rock fragmentation, V c represents the vegetation coverage, Bg represents the probability of debris flow caused by bedrock vulnerability, η, ν and θ represent the slope S, soil moisture W, respectively. s and vegetation coverage V c The weight value of The hydrodynamic pressure coefficient HPC is calculated by the following formula: Where Q represents the surface runoff flow, D represents the water depth, and S e represents the slope effect, A f represents the river basin area, A max represents the watershed area normalization factor; The risk assessment module is used to evaluate the risk level of debris flow occurrence based on the model output results by comparing the debris flow disaster risk index MRI with the preset first safety threshold M and second safety threshold N, and classify and manage different areas; The early warning and emergency response module is used to issue debris flow warnings based on real-time monitoring data and risk assessment results. Warning information is transmitted to relevant departments and the public through text messages, alarms, and application notifications, supporting automated emergency response measures, including road closures and evacuations. The model optimization module is used to self-adjust and optimize the debris flow prediction model using historical data and real-time feedback.

2. The regional geological disaster risk intelligent assessment system according to claim 1, characterized in that: The data acquisition module includes a meteorological data acquisition unit, a geological data acquisition unit and a hydrological data acquisition unit; The meteorological data acquisition unit is used to collect meteorological data related to debris flow in real time by integrating automatic rain gauge, weather station and radar rainfall monitoring system, including rainfall amount, rainfall intensity and rainfall duration, to obtain: total rainfall P t , rainfall intensity I r and the cumulative rainfall threshold P th ; The geological data acquisition unit is used to collect data related to geological fragility in real time by integrating GPS equipment, laser rangefinder and soil moisture sensor, including terrain slope, soil moisture content and rock fragmentation, to obtain: slope S, soil moisture W s , rock crushing degree R f and vegetation coverage V c ; The hydrological data acquisition unit is used to collect hydrological data related to hydrodynamic pressure in real time through a flow meter, an ultrasonic water level meter and a pressure sensor, including surface water flow, water depth and river runoff information, to obtain: surface runoff flow Q, water depth D, slope effect S e , River Basin Area A f and the watershed area normalization factor A max .

3. The regional geological disaster risk intelligent assessment system according to claim 2, characterized in that: The data preprocessing module includes a data preprocessing unit; The data preprocessing unit is used to clean the collected raw data, remove noise and invalid data, convert the cleaned data into a unified format, ensure that data from different sources can be compatible in subsequent analysis, complete missing data, process missing key data points through interpolation or machine learning algorithms, and store them in a data storage system.

4. The regional geological disaster risk intelligent assessment system according to claim 1, characterized in that: The risk assessment module includes a threshold comparison unit and a regional risk classification unit; The threshold comparison unit is used to compare the debris flow disaster risk index MRI with the preset first safety threshold M and second safety threshold N to evaluate the risk level of debris flow: When the debris flow disaster risk index MRI is less than or equal to the first safety threshold M, it is assessed as the first risk level. Within this range, the probability of debris flow occurrence is less than 30%, and it does not pose a threat to people, infrastructure and ecological environment in the area. Under this condition, the system maintains routine monitoring and no emergency response measures are required; When the debris flow risk index MRI is greater than the first safety threshold M and less than or equal to the second safety threshold N, it is assessed as the second risk level. At this time, the probability of debris flow occurrence is 40%-50%. It is recommended to strengthen monitoring and remind relevant departments to take preventive measures, including raising the warning level, initiating local emergency preparations, and closely monitoring weather and geological changes in high-risk areas. When the debris flow disaster risk index MRI is greater than the second safety threshold N, it is assessed as the third risk level. At this time, the risk of debris flow is greater than 50%. The emergency response mechanism needs to be immediately activated, relevant departments need to be notified, and the public needs to be warned. Road closures, personnel evacuations, and emergency deployment of rescue resources are required to ensure personal safety and minimize property losses. The regional risk classification unit is used to classify and manage monitoring areas based on different risk levels and determine the priority of each area to facilitate the planning and execution of subsequent emergency responses.

5. The regional geological disaster risk intelligent assessment system according to claim 1, characterized in that: The early warning emergency response module includes an early warning generation unit and an emergency measure execution unit; The warning generation unit is used to automatically generate debris flow warning information based on real-time monitoring data and risk assessment results, including detailed content of potential risks and the scope of the affected area, and transmit the debris flow warning information to relevant government departments and the public through SMS, alarm bells and application notification channels; The emergency measures execution unit is used to automatically trigger preset emergency response measures according to the early warning information, including closing roads in the affected area, evacuating people and initiating the deployment of rescue resources.

6. The regional geological disaster risk intelligent assessment system according to claim 1, characterized in that: The model optimization module includes a historical data feedback unit and a model adjustment unit; The historical data feedback unit is used to collect historical data and feedback information after the debris flow disaster occurs, and optimize and adaptively adjust the parameters of the existing physical model and machine learning model based on the feedback data; The model adjustment unit is used to continuously update and iterate the model based on new data during system operation to ensure the adaptability and robustness of the debris flow risk prediction model under different environments and conditions.

7. A method for intelligently assessing the risk of regional geological hazards, applied to a system for intelligently assessing the risk of regional geological hazards according to any one of claims 1 to 6, characterized in that: The following steps are involved: Step 1: Collect a variety of real-time data related to debris flows, including meteorological data, geological data, and hydrological data, by integrating real-time sensors and satellite remote sensing data; Step 2: Clean, format, and reduce noise of the original data, complete missing data, remove abnormal data, and store it in the data storage system; Step 3: Based on the collected data, a physical model and a machine learning model are constructed to calculate the following: debris flow risk index MRI, rainfall intensity coefficient RIC, geological vulnerability coefficient GVC, and hydrodynamic pressure coefficient HPC. The probability of debris flow occurrence is predicted by the model, which combines key parameters such as topography, rainfall, and soil moisture for analysis. Step 4: Based on the model output, the debris flow disaster risk index MRI is compared with the preset first safety threshold M and second safety threshold N to assess the risk level of debris flow and classify and manage different areas; Step 5: Based on real-time monitoring data and risk assessment results, a debris flow warning is issued. Warning information is transmitted to relevant departments and the public via text messages, alarms, and app notifications, supporting automated emergency response measures, including road closures and evacuations. Step 6: Use historical data and real-time feedback to self-adjust and optimize the debris flow prediction model.

Images